Japanese Character Segmentation for Historical Handwritten Official Documents Using Fully Convolutional Networks.
Kei WatanabeShinji TakahashiYuki KamayaMasashi YamadaYoshito MekadaJun-ichi HasegawaShinya MiyazakiPublished in: ICDAR (2019)
Keyphrases
- character segmentation
- printed documents
- character recognition
- optical character recognition
- historical manuscripts
- historical documents
- chinese characters
- word spotting
- hand written
- document analysis
- automatic recognition
- gray scale images
- document images
- handwriting recognition
- document collections
- machine vision
- license plate
- document processing
- handwritten text
- word recognition
- handwritten documents
- language independent
- document clustering
- document retrieval
- information retrieval
- metadata
- complex networks
- retrieval systems
- handwritten characters
- gray scale
- web documents
- information retrieval systems
- document image analysis
- text documents
- language model
- vehicle license plate